In accordance with regulations and requirements, the editorial department's website domain has been changed to arocmag.cn. The original domain (arocmag.com) will be discontinued after Dec. 31st, 2024.
See More
Algorithm Research & Explore
|
App. Res. of Comp. Printed Article
Vol. 37, 2020 No. 9
2586-2590,2599

Graph representation learning based on graph partition sampling algorithm

Xia Xin1
Gao Pin2
Chen Kang1
Jiang Jinlei1
1. Dept. of Computer Science & Technology, Tsinghua University, Beijing 100084, China
2. WeChat Group, Tencent Corporation, Shenzhen Guangdong 518057, China
DOI: 10.19734/j.issn.1001-3695.2019.03.0130

Abstract

When training graph embedding via neural network, high dimension feature vector and large scale graph cause data transferring from memory to GPU to be a bottleneck. Aimed to solve this problem, this paper proposed graph partition based graph representation learning. This method splitted graph nodes into blocks according to their degree. It stored several node feature matrices in buffer pool on GPU. Every epoch, it trained representation during several blocks which fitted into buffer pool to reduce the data transferred from memory to GPU. Based on block split, this method used blocked based sampling algorithm, cached block feature matrix in GPU buffer pool to reduce memory read and built hierarchical negative sampling table, which could sample nodes in const time complex. Compared to related work on several real world datasets, this method achieves competitive accuracy at downstream machine learning task and 2~7 times speedup on training process. The experiments show that graph representation learning based on partition can train model efficiently and generate accurate embedding vectors. In future work, it is worth to prove the deviation between partition based method and original method in theory.

Foundation Support

国家重点研发计划资助项目(2018YFB1003505)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2019.03.0130
Publish at: Application Research of Computers Printed Article, Vol. 37, 2020 No. 9
Section: Algorithm Research & Explore
Pages: 2586-2590,2599
Serial Number: 1001-3695(2020)09-004-2586-05

Publish History

[2020-09-05] Printed Article

Cite This Article

夏鑫, 高品, 陈康, 等. 基于图划分抽样算法的图表示学习 [J]. 计算机应用研究, 2020, 37 (9): 2586-2590,2599. (Xia Xin, Gao Pin, Chen Kang, et al. Graph representation learning based on graph partition sampling algorithm [J]. Application Research of Computers, 2020, 37 (9): 2586-2590,2599. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)